Multi-objective optimization intelligent operation control prediction method for new power supply trains

Abstract

The invention discloses a multi-objective optimization intelligent operation control prediction method for new-type power supply trains. The original data is obtained from the static and dynamic big data of the new power supply train, and the train information sequence data is obtained by parameterization / regularization and normalization; the train operation status data under ideal conditions is obtained by using the local data in the train information sequence data; input to the long The basic model is obtained by training in the short-term memory network, and the train information sequence data is divided into multiple parts, which are input into the basic model in turn and trained again to obtain the basic model with knowledge; the square loss training is established; the speed of real collection Input into the basic model with knowledge to predict the output to obtain the traction of the next moment. The invention does not rely on a large amount of data, reduces the amount of training data, obtains a model conforming to the distribution of real train operation data, improves the accuracy of the model and is convenient for direct use in real applications.

Description

technical field [0001] The invention relates to an industrial control operation prediction regression method in the field of computer deep learning, and in particular to a multi-objective optimization intelligent operation control prediction method for new-type power supply trains. Background technique [0002] The train operation control model oriented to multi-objective optimization is novel in technology, involves many parameters and complex correlations, and the traditional modeling method based on mechanism and expert knowledge is difficult to deal with. To do this, a data-driven machine learning approach is needed to build relevant models. [0003] The train operation control directly affects the energy consumption during the train operation. In order to ensure the normal operation of the train, in the process of solving the multi-objective optimization-oriented train operation control strategy, it is necessary to use the parameters of the train power supply system as ...

AI Technical Summary

Problems solved by technology

[0005] Therefore, the operation control of the new power supply train has many parameters, complex correlations, and little available data, making it difficult to directly build a model

The traditional modeling method based on mechanism and expert knowledge has long modeling time and high cost, and the accuracy of the model does not support direct use in actual scenarios

Images